Scene-aware Far-field Automatic Speech Recognition
arXiv:2104.10757
Abstract
We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the sub-band reverberation time of an environment from its speech samples. We model the acoustic characteristics of a scene with its reverberation time and represent it using a multivariate Gaussian distribution. We use this distribution to select acoustic impulse responses from a large real-world dataset for augmenting speech data. The speech recognition system trained on our scene-aware data consistently outperforms the system trained using many more random acoustic impulse responses on the REVERB and the AMI far-field benchmarks. In practice, we obtain 2.64% absolute improvement in word error rate compared with using training data of the same size with uniformly distributed reverberation times.
References in corpus (6)
- Building and Evaluation of a Real Room Impulse Response Dataset
- Scene-Aware Audio Rendering via Deep Acoustic Analysis
- Improving Reverberant Speech Training Using Diffuse Acoustic Simulation
- Low-frequency Compensated Synthetic Impulse Responses for Improved Far-field Speech Recognition
- An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
- Toward Cross-Domain Speech Recognition with End-to-End Models